AUROC: 0.902F1: 0.699
Papers with Code · CC BY-SA 4.0
Anomaly Detection
Anomaly Detection is a binary classification identifying unusual or unexpected patterns in a dataset, which deviate significantly from the majority of the data. The goal of anomaly detection is to identify such anomalies, which could represent errors, fraud, or other types of unusual events, and flag them for further investigation.
[Image source]: GAN-based Anomaly Detection in Imbalance Problems
논문
AUC: 98.65
AUCROC: 0.99
ROC AUC: 95.0
Detection AUROC: 93.7Segmentation AUROC: 97.6
AUC: 97.4%
Segmentation AUPRO: 93.75
AUC: 97.1%
AP: 89.1FPR95: 8.8
AUC: 90.2%
AP: 85.6FPR95: 9.8
AUC: 96.3%FPS: 195
ROC AUC: 98.6
ROC AUC: 95.6
AP: 41.83FPR95: 59.72
AP: 45.10FPR95: 44.58
AP: 90.28FPR95: 4.92
AP: 71.61FPR95: 17.74
F1-Score: 59.19
AUC: 95.4%FPS: 1655
AP: 25.82FPR95: 49.74
AUC: 97.5
AP: 24.86FPR95: 64.69
UniNet: A Contrastive Learning-guided Unified Framework with Feature Selection for Anomaly Detection
AUC: 97.9
AP: 79.70FPR95: 13.45
AUC: 97.74